debian/copyright: Fix missing-license-paragraph-in-dep5-copyright.

[youtubedl] / youtube_dl / extractor / appletrailers.py
diff --git a/youtube_dl/extractor/appletrailers.py b/youtube_dl/extractor/appletrailers.py

index dc8657b67c9850c1676af737f319cb4c06bad6d6..0c01fa1a13ffa6fbfbfe7b7fb2283d5ed4f8b70f 100644 (file)
--- a/youtube_dl/extractor/appletrailers.py
+++ b/youtube_dl/extractor/appletrailers.py
@@ -6,6 +6,7 @@ import json
  from .common import InfoExtractor
  from ..utils import (
      compat_urlparse,
  from .common import InfoExtractor
  from ..utils import (
      compat_urlparse,
+    int_or_none,
  )
  
  
  )
  
  
@@ -69,15 +70,17 @@ class AppleTrailersIE(InfoExtractor):
          uploader_id = mobj.group('company')
  
          playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
          uploader_id = mobj.group('company')
  
          playlist_url = compat_urlparse.urljoin(url, 'includes/playlists/itunes.inc')
+
          def fix_html(s):
              s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
              s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
              # The ' in the onClick attributes are not escaped, it couldn't be parsed
              # like: http://trailers.apple.com/trailers/wb/gravity/
          def fix_html(s):
              s = re.sub(r'(?s)<script[^<]*?>.*?</script>', '', s)
              s = re.sub(r'<img ([^<]*?)>', r'<img \1/>', s)
              # The ' in the onClick attributes are not escaped, it couldn't be parsed
              # like: http://trailers.apple.com/trailers/wb/gravity/
+
              def _clean_json(m):
                  return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
              s = re.sub(self._JSON_RE, _clean_json, s)
              def _clean_json(m):
                  return 'iTunes.playURL(%s);' % m.group(1).replace('\'', '&#39;')
              s = re.sub(self._JSON_RE, _clean_json, s)
-            s = '<html>' + s + u'</html>'
+            s = '<html>%s</html>' % s
              return s
          doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
  
              return s
          doc = self._download_xml(playlist_url, movie, transform_source=fix_html)
  
@@ -85,7 +88,7 @@ class AppleTrailersIE(InfoExtractor):
          for li in doc.findall('./div/ul/li'):
              on_click = li.find('.//a').attrib['onClick']
              trailer_info_json = self._search_regex(self._JSON_RE,
          for li in doc.findall('./div/ul/li'):
              on_click = li.find('.//a').attrib['onClick']
              trailer_info_json = self._search_regex(self._JSON_RE,
-                on_click, 'trailer info')
+                                                   on_click, 'trailer info')
              trailer_info = json.loads(trailer_info_json)
              title = trailer_info['title']
              video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
              trailer_info = json.loads(trailer_info_json)
              title = trailer_info['title']
              video_id = movie + '-' + re.sub(r'[^a-zA-Z0-9]', '', title).lower()
@@ -110,8 +113,8 @@ class AppleTrailersIE(InfoExtractor):
                  formats.append({
                      'url': format_url,
                      'format': format['type'],
                  formats.append({
                      'url': format_url,
                      'format': format['type'],
-                    'width': format['width'],
-                    'height': int(format['height']),
+                    'width': int_or_none(format['width']),
+                    'height': int_or_none(format['height']),
                  })
  
              self._sort_formats(formats)
                  })
  
              self._sort_formats(formats)